Kukutla Manohar
21BCE9466 VIT-AP

In [1]:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
In [2]:
df=pd.read_csv("C:/Users/Manu/Downloads/WA_Fn-UseC_-HR-Employee-Attrition.csv")
In [3]:
df.head()
Out[3]:
Age Attrition BusinessTravel DailyRate Department DistanceFromHome Education EducationField EmployeeCount EmployeeNumber ... RelationshipSatisfaction StandardHours StockOptionLevel TotalWorkingYears TrainingTimesLastYear WorkLifeBalance YearsAtCompany YearsInCurrentRole YearsSinceLastPromotion YearsWithCurrManager
0 41 Yes Travel_Rarely 1102 Sales 1 2 Life Sciences 1 1 ... 1 80 0 8 0 1 6 4 0 5
1 49 No Travel_Frequently 279 Research & Development 8 1 Life Sciences 1 2 ... 4 80 1 10 3 3 10 7 1 7
2 37 Yes Travel_Rarely 1373 Research & Development 2 2 Other 1 4 ... 2 80 0 7 3 3 0 0 0 0
3 33 No Travel_Frequently 1392 Research & Development 3 4 Life Sciences 1 5 ... 3 80 0 8 3 3 8 7 3 0
4 27 No Travel_Rarely 591 Research & Development 2 1 Medical 1 7 ... 4 80 1 6 3 3 2 2 2 2

5 rows × 35 columns

In [4]:
df.describe()
Out[4]:
Age DailyRate DistanceFromHome Education EmployeeCount EmployeeNumber EnvironmentSatisfaction HourlyRate JobInvolvement JobLevel ... RelationshipSatisfaction StandardHours StockOptionLevel TotalWorkingYears TrainingTimesLastYear WorkLifeBalance YearsAtCompany YearsInCurrentRole YearsSinceLastPromotion YearsWithCurrManager
count 1470.000000 1470.000000 1470.000000 1470.000000 1470.0 1470.000000 1470.000000 1470.000000 1470.000000 1470.000000 ... 1470.000000 1470.0 1470.000000 1470.000000 1470.000000 1470.000000 1470.000000 1470.000000 1470.000000 1470.000000
mean 36.923810 802.485714 9.192517 2.912925 1.0 1024.865306 2.721769 65.891156 2.729932 2.063946 ... 2.712245 80.0 0.793878 11.279592 2.799320 2.761224 7.008163 4.229252 2.187755 4.123129
std 9.135373 403.509100 8.106864 1.024165 0.0 602.024335 1.093082 20.329428 0.711561 1.106940 ... 1.081209 0.0 0.852077 7.780782 1.289271 0.706476 6.126525 3.623137 3.222430 3.568136
min 18.000000 102.000000 1.000000 1.000000 1.0 1.000000 1.000000 30.000000 1.000000 1.000000 ... 1.000000 80.0 0.000000 0.000000 0.000000 1.000000 0.000000 0.000000 0.000000 0.000000
25% 30.000000 465.000000 2.000000 2.000000 1.0 491.250000 2.000000 48.000000 2.000000 1.000000 ... 2.000000 80.0 0.000000 6.000000 2.000000 2.000000 3.000000 2.000000 0.000000 2.000000
50% 36.000000 802.000000 7.000000 3.000000 1.0 1020.500000 3.000000 66.000000 3.000000 2.000000 ... 3.000000 80.0 1.000000 10.000000 3.000000 3.000000 5.000000 3.000000 1.000000 3.000000
75% 43.000000 1157.000000 14.000000 4.000000 1.0 1555.750000 4.000000 83.750000 3.000000 3.000000 ... 4.000000 80.0 1.000000 15.000000 3.000000 3.000000 9.000000 7.000000 3.000000 7.000000
max 60.000000 1499.000000 29.000000 5.000000 1.0 2068.000000 4.000000 100.000000 4.000000 5.000000 ... 4.000000 80.0 3.000000 40.000000 6.000000 4.000000 40.000000 18.000000 15.000000 17.000000

8 rows × 26 columns

Data Preprocessing¶

In [5]:
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1470 entries, 0 to 1469
Data columns (total 35 columns):
 #   Column                    Non-Null Count  Dtype 
---  ------                    --------------  ----- 
 0   Age                       1470 non-null   int64 
 1   Attrition                 1470 non-null   object
 2   BusinessTravel            1470 non-null   object
 3   DailyRate                 1470 non-null   int64 
 4   Department                1470 non-null   object
 5   DistanceFromHome          1470 non-null   int64 
 6   Education                 1470 non-null   int64 
 7   EducationField            1470 non-null   object
 8   EmployeeCount             1470 non-null   int64 
 9   EmployeeNumber            1470 non-null   int64 
 10  EnvironmentSatisfaction   1470 non-null   int64 
 11  Gender                    1470 non-null   object
 12  HourlyRate                1470 non-null   int64 
 13  JobInvolvement            1470 non-null   int64 
 14  JobLevel                  1470 non-null   int64 
 15  JobRole                   1470 non-null   object
 16  JobSatisfaction           1470 non-null   int64 
 17  MaritalStatus             1470 non-null   object
 18  MonthlyIncome             1470 non-null   int64 
 19  MonthlyRate               1470 non-null   int64 
 20  NumCompaniesWorked        1470 non-null   int64 
 21  Over18                    1470 non-null   object
 22  OverTime                  1470 non-null   object
 23  PercentSalaryHike         1470 non-null   int64 
 24  PerformanceRating         1470 non-null   int64 
 25  RelationshipSatisfaction  1470 non-null   int64 
 26  StandardHours             1470 non-null   int64 
 27  StockOptionLevel          1470 non-null   int64 
 28  TotalWorkingYears         1470 non-null   int64 
 29  TrainingTimesLastYear     1470 non-null   int64 
 30  WorkLifeBalance           1470 non-null   int64 
 31  YearsAtCompany            1470 non-null   int64 
 32  YearsInCurrentRole        1470 non-null   int64 
 33  YearsSinceLastPromotion   1470 non-null   int64 
 34  YearsWithCurrManager      1470 non-null   int64 
dtypes: int64(26), object(9)
memory usage: 402.1+ KB
In [7]:
df.corr()

C:\Users\Manu\AppData\Local\Temp\ipykernel_13256\1134722465.py:1: FutureWarning: The default value of numeric_only in DataFrame.corr is deprecated. In a future version, it will default to False. Select only valid columns or specify the value of numeric_only to silence this warning.
  df.corr()
Out[7]:
Age DailyRate DistanceFromHome Education EmployeeCount EmployeeNumber EnvironmentSatisfaction HourlyRate JobInvolvement JobLevel ... RelationshipSatisfaction StandardHours StockOptionLevel TotalWorkingYears TrainingTimesLastYear WorkLifeBalance YearsAtCompany YearsInCurrentRole YearsSinceLastPromotion YearsWithCurrManager
Age 1.000000 0.010661 -0.001686 0.208034 NaN -0.010145 0.010146 0.024287 0.029820 0.509604 ... 0.053535 NaN 0.037510 0.680381 -0.019621 -0.021490 0.311309 0.212901 0.216513 0.202089
DailyRate 0.010661 1.000000 -0.004985 -0.016806 NaN -0.050990 0.018355 0.023381 0.046135 0.002966 ... 0.007846 NaN 0.042143 0.014515 0.002453 -0.037848 -0.034055 0.009932 -0.033229 -0.026363
DistanceFromHome -0.001686 -0.004985 1.000000 0.021042 NaN 0.032916 -0.016075 0.031131 0.008783 0.005303 ... 0.006557 NaN 0.044872 0.004628 -0.036942 -0.026556 0.009508 0.018845 0.010029 0.014406
Education 0.208034 -0.016806 0.021042 1.000000 NaN 0.042070 -0.027128 0.016775 0.042438 0.101589 ... -0.009118 NaN 0.018422 0.148280 -0.025100 0.009819 0.069114 0.060236 0.054254 0.069065
EmployeeCount NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
EmployeeNumber -0.010145 -0.050990 0.032916 0.042070 NaN 1.000000 0.017621 0.035179 -0.006888 -0.018519 ... -0.069861 NaN 0.062227 -0.014365 0.023603 0.010309 -0.011240 -0.008416 -0.009019 -0.009197
EnvironmentSatisfaction 0.010146 0.018355 -0.016075 -0.027128 NaN 0.017621 1.000000 -0.049857 -0.008278 0.001212 ... 0.007665 NaN 0.003432 -0.002693 -0.019359 0.027627 0.001458 0.018007 0.016194 -0.004999
HourlyRate 0.024287 0.023381 0.031131 0.016775 NaN 0.035179 -0.049857 1.000000 0.042861 -0.027853 ... 0.001330 NaN 0.050263 -0.002334 -0.008548 -0.004607 -0.019582 -0.024106 -0.026716 -0.020123
JobInvolvement 0.029820 0.046135 0.008783 0.042438 NaN -0.006888 -0.008278 0.042861 1.000000 -0.012630 ... 0.034297 NaN 0.021523 -0.005533 -0.015338 -0.014617 -0.021355 0.008717 -0.024184 0.025976
JobLevel 0.509604 0.002966 0.005303 0.101589 NaN -0.018519 0.001212 -0.027853 -0.012630 1.000000 ... 0.021642 NaN 0.013984 0.782208 -0.018191 0.037818 0.534739 0.389447 0.353885 0.375281
JobSatisfaction -0.004892 0.030571 -0.003669 -0.011296 NaN -0.046247 -0.006784 -0.071335 -0.021476 -0.001944 ... -0.012454 NaN 0.010690 -0.020185 -0.005779 -0.019459 -0.003803 -0.002305 -0.018214 -0.027656
MonthlyIncome 0.497855 0.007707 -0.017014 0.094961 NaN -0.014829 -0.006259 -0.015794 -0.015271 0.950300 ... 0.025873 NaN 0.005408 0.772893 -0.021736 0.030683 0.514285 0.363818 0.344978 0.344079
MonthlyRate 0.028051 -0.032182 0.027473 -0.026084 NaN 0.012648 0.037600 -0.015297 -0.016322 0.039563 ... -0.004085 NaN -0.034323 0.026442 0.001467 0.007963 -0.023655 -0.012815 0.001567 -0.036746
NumCompaniesWorked 0.299635 0.038153 -0.029251 0.126317 NaN -0.001251 0.012594 0.022157 0.015012 0.142501 ... 0.052733 NaN 0.030075 0.237639 -0.066054 -0.008366 -0.118421 -0.090754 -0.036814 -0.110319
PercentSalaryHike 0.003634 0.022704 0.040235 -0.011111 NaN -0.012944 -0.031701 -0.009062 -0.017205 -0.034730 ... -0.040490 NaN 0.007528 -0.020608 -0.005221 -0.003280 -0.035991 -0.001520 -0.022154 -0.011985
PerformanceRating 0.001904 0.000473 0.027110 -0.024539 NaN -0.020359 -0.029548 -0.002172 -0.029071 -0.021222 ... -0.031351 NaN 0.003506 0.006744 -0.015579 0.002572 0.003435 0.034986 0.017896 0.022827
RelationshipSatisfaction 0.053535 0.007846 0.006557 -0.009118 NaN -0.069861 0.007665 0.001330 0.034297 0.021642 ... 1.000000 NaN -0.045952 0.024054 0.002497 0.019604 0.019367 -0.015123 0.033493 -0.000867
StandardHours NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
StockOptionLevel 0.037510 0.042143 0.044872 0.018422 NaN 0.062227 0.003432 0.050263 0.021523 0.013984 ... -0.045952 NaN 1.000000 0.010136 0.011274 0.004129 0.015058 0.050818 0.014352 0.024698
TotalWorkingYears 0.680381 0.014515 0.004628 0.148280 NaN -0.014365 -0.002693 -0.002334 -0.005533 0.782208 ... 0.024054 NaN 0.010136 1.000000 -0.035662 0.001008 0.628133 0.460365 0.404858 0.459188
TrainingTimesLastYear -0.019621 0.002453 -0.036942 -0.025100 NaN 0.023603 -0.019359 -0.008548 -0.015338 -0.018191 ... 0.002497 NaN 0.011274 -0.035662 1.000000 0.028072 0.003569 -0.005738 -0.002067 -0.004096
WorkLifeBalance -0.021490 -0.037848 -0.026556 0.009819 NaN 0.010309 0.027627 -0.004607 -0.014617 0.037818 ... 0.019604 NaN 0.004129 0.001008 0.028072 1.000000 0.012089 0.049856 0.008941 0.002759
YearsAtCompany 0.311309 -0.034055 0.009508 0.069114 NaN -0.011240 0.001458 -0.019582 -0.021355 0.534739 ... 0.019367 NaN 0.015058 0.628133 0.003569 0.012089 1.000000 0.758754 0.618409 0.769212
YearsInCurrentRole 0.212901 0.009932 0.018845 0.060236 NaN -0.008416 0.018007 -0.024106 0.008717 0.389447 ... -0.015123 NaN 0.050818 0.460365 -0.005738 0.049856 0.758754 1.000000 0.548056 0.714365
YearsSinceLastPromotion 0.216513 -0.033229 0.010029 0.054254 NaN -0.009019 0.016194 -0.026716 -0.024184 0.353885 ... 0.033493 NaN 0.014352 0.404858 -0.002067 0.008941 0.618409 0.548056 1.000000 0.510224
YearsWithCurrManager 0.202089 -0.026363 0.014406 0.069065 NaN -0.009197 -0.004999 -0.020123 0.025976 0.375281 ... -0.000867 NaN 0.024698 0.459188 -0.004096 0.002759 0.769212 0.714365 0.510224 1.000000

26 rows × 26 columns

In [8]:
df.corr().DailyRate.sort_values(ascending=False)

C:\Users\Manu\AppData\Local\Temp\ipykernel_13256\2954484028.py:1: FutureWarning: The default value of numeric_only in DataFrame.corr is deprecated. In a future version, it will default to False. Select only valid columns or specify the value of numeric_only to silence this warning.
  df.corr().DailyRate.sort_values(ascending=False)
Out[8]:
DailyRate                   1.000000
JobInvolvement              0.046135
StockOptionLevel            0.042143
NumCompaniesWorked          0.038153
JobSatisfaction             0.030571
HourlyRate                  0.023381
PercentSalaryHike           0.022704
EnvironmentSatisfaction     0.018355
TotalWorkingYears           0.014515
Age                         0.010661
YearsInCurrentRole          0.009932
RelationshipSatisfaction    0.007846
MonthlyIncome               0.007707
JobLevel                    0.002966
TrainingTimesLastYear       0.002453
PerformanceRating           0.000473
DistanceFromHome           -0.004985
Education                  -0.016806
YearsWithCurrManager       -0.026363
MonthlyRate                -0.032182
YearsSinceLastPromotion    -0.033229
YearsAtCompany             -0.034055
WorkLifeBalance            -0.037848
EmployeeNumber             -0.050990
EmployeeCount                    NaN
StandardHours                    NaN
Name: DailyRate, dtype: float64
In [9]:
df.isnull().any()
Out[9]:
Age                         False
Attrition                   False
BusinessTravel              False
DailyRate                   False
Department                  False
DistanceFromHome            False
Education                   False
EducationField              False
EmployeeCount               False
EmployeeNumber              False
EnvironmentSatisfaction     False
Gender                      False
HourlyRate                  False
JobInvolvement              False
JobLevel                    False
JobRole                     False
JobSatisfaction             False
MaritalStatus               False
MonthlyIncome               False
MonthlyRate                 False
NumCompaniesWorked          False
Over18                      False
OverTime                    False
PercentSalaryHike           False
PerformanceRating           False
RelationshipSatisfaction    False
StandardHours               False
StockOptionLevel            False
TotalWorkingYears           False
TrainingTimesLastYear       False
WorkLifeBalance             False
YearsAtCompany              False
YearsInCurrentRole          False
YearsSinceLastPromotion     False
YearsWithCurrManager        False
dtype: bool
In [10]:
df.isnull().sum()
Out[10]:
Age                         0
Attrition                   0
BusinessTravel              0
DailyRate                   0
Department                  0
DistanceFromHome            0
Education                   0
EducationField              0
EmployeeCount               0
EmployeeNumber              0
EnvironmentSatisfaction     0
Gender                      0
HourlyRate                  0
JobInvolvement              0
JobLevel                    0
JobRole                     0
JobSatisfaction             0
MaritalStatus               0
MonthlyIncome               0
MonthlyRate                 0
NumCompaniesWorked          0
Over18                      0
OverTime                    0
PercentSalaryHike           0
PerformanceRating           0
RelationshipSatisfaction    0
StandardHours               0
StockOptionLevel            0
TotalWorkingYears           0
TrainingTimesLastYear       0
WorkLifeBalance             0
YearsAtCompany              0
YearsInCurrentRole          0
YearsSinceLastPromotion     0
YearsWithCurrManager        0
dtype: int64
In [11]:
sns.histplot(df['DailyRate'], bins=20, kde=True)
plt.show()
In [12]:
plt.scatter(df["YearsAtCompany"],df["TotalWorkingYears"])
Out[12]:
<matplotlib.collections.PathCollection at 0x1aab36a1110>
In [13]:
sns.heatmap(df.corr(),annot=True)

C:\Users\Manu\AppData\Local\Temp\ipykernel_13256\4277794465.py:1: FutureWarning: The default value of numeric_only in DataFrame.corr is deprecated. In a future version, it will default to False. Select only valid columns or specify the value of numeric_only to silence this warning.
  sns.heatmap(df.corr(),annot=True)
Out[13]:
<Axes: >
In [16]:
sns.pairplot(df)
Out[16]:
<seaborn.axisgrid.PairGrid at 0x1aad8b31150>
In [20]:
gender_count = df['Gender'].value_counts()
sns.barplot(x=gender_count.index, y=gender_count.values)
plt.show()
In [21]:
sns.boxplot(df.DailyRate)
Out[21]:
<Axes: >
In [22]:
sns.boxplot(df.DistanceFromHome)
Out[22]:
<Axes: >
In [23]:
df.head()
Out[23]:
Age Attrition BusinessTravel DailyRate Department DistanceFromHome Education EducationField EmployeeCount EmployeeNumber ... RelationshipSatisfaction StandardHours StockOptionLevel TotalWorkingYears TrainingTimesLastYear WorkLifeBalance YearsAtCompany YearsInCurrentRole YearsSinceLastPromotion YearsWithCurrManager
0 41 Yes Travel_Rarely 1102 Sales 1 2 Life Sciences 1 1 ... 1 80 0 8 0 1 6 4 0 5
1 49 No Travel_Frequently 279 Research & Development 8 1 Life Sciences 1 2 ... 4 80 1 10 3 3 10 7 1 7
2 37 Yes Travel_Rarely 1373 Research & Development 2 2 Other 1 4 ... 2 80 0 7 3 3 0 0 0 0
3 33 No Travel_Frequently 1392 Research & Development 3 4 Life Sciences 1 5 ... 3 80 0 8 3 3 8 7 3 0
4 27 No Travel_Rarely 591 Research & Development 2 1 Medical 1 7 ... 4 80 1 6 3 3 2 2 2 2

5 rows × 35 columns

In [24]:
x = df.drop('Attrition', axis=1)
x.head()
Out[24]:
Age BusinessTravel DailyRate Department DistanceFromHome Education EducationField EmployeeCount EmployeeNumber EnvironmentSatisfaction ... RelationshipSatisfaction StandardHours StockOptionLevel TotalWorkingYears TrainingTimesLastYear WorkLifeBalance YearsAtCompany YearsInCurrentRole YearsSinceLastPromotion YearsWithCurrManager
0 41 Travel_Rarely 1102 Sales 1 2 Life Sciences 1 1 2 ... 1 80 0 8 0 1 6 4 0 5
1 49 Travel_Frequently 279 Research & Development 8 1 Life Sciences 1 2 3 ... 4 80 1 10 3 3 10 7 1 7
2 37 Travel_Rarely 1373 Research & Development 2 2 Other 1 4 4 ... 2 80 0 7 3 3 0 0 0 0
3 33 Travel_Frequently 1392 Research & Development 3 4 Life Sciences 1 5 4 ... 3 80 0 8 3 3 8 7 3 0
4 27 Travel_Rarely 591 Research & Development 2 1 Medical 1 7 1 ... 4 80 1 6 3 3 2 2 2 2

5 rows × 34 columns

In [25]:
x.head()
Out[25]:
Age BusinessTravel DailyRate Department DistanceFromHome Education EducationField EmployeeCount EmployeeNumber EnvironmentSatisfaction ... RelationshipSatisfaction StandardHours StockOptionLevel TotalWorkingYears TrainingTimesLastYear WorkLifeBalance YearsAtCompany YearsInCurrentRole YearsSinceLastPromotion YearsWithCurrManager
0 41 Travel_Rarely 1102 Sales 1 2 Life Sciences 1 1 2 ... 1 80 0 8 0 1 6 4 0 5
1 49 Travel_Frequently 279 Research & Development 8 1 Life Sciences 1 2 3 ... 4 80 1 10 3 3 10 7 1 7
2 37 Travel_Rarely 1373 Research & Development 2 2 Other 1 4 4 ... 2 80 0 7 3 3 0 0 0 0
3 33 Travel_Frequently 1392 Research & Development 3 4 Life Sciences 1 5 4 ... 3 80 0 8 3 3 8 7 3 0
4 27 Travel_Rarely 591 Research & Development 2 1 Medical 1 7 1 ... 4 80 1 6 3 3 2 2 2 2

5 rows × 34 columns

In [26]:
x.shape
Out[26]:
(1470, 34)
In [27]:
type(x)
Out[27]:
pandas.core.frame.DataFrame
In [28]:
y = df['Attrition']
y.head()
Out[28]:
0    Yes
1     No
2    Yes
3     No
4     No
Name: Attrition, dtype: object
In [29]:
from sklearn.preprocessing import LabelEncoder
le=LabelEncoder()
In [30]:
x["BusinessTravel"]=le.fit_transform(x["BusinessTravel"])
x["Department"]=le.fit_transform(x["Department"])
x["EducationField"]=le.fit_transform(x["EducationField"])
x["Gender"]=le.fit_transform(x["Gender"])
x["JobRole"]=le.fit_transform(x["JobRole"])
x["MaritalStatus"]=le.fit_transform(x["MaritalStatus"])
x["Over18"]=le.fit_transform(x["Over18"])
x["OverTime"]=le.fit_transform(x["OverTime"])
In [31]:
x.head()
Out[31]:
Age BusinessTravel DailyRate Department DistanceFromHome Education EducationField EmployeeCount EmployeeNumber EnvironmentSatisfaction ... RelationshipSatisfaction StandardHours StockOptionLevel TotalWorkingYears TrainingTimesLastYear WorkLifeBalance YearsAtCompany YearsInCurrentRole YearsSinceLastPromotion YearsWithCurrManager
0 41 2 1102 2 1 2 1 1 1 2 ... 1 80 0 8 0 1 6 4 0 5
1 49 1 279 1 8 1 1 1 2 3 ... 4 80 1 10 3 3 10 7 1 7
2 37 2 1373 1 2 2 4 1 4 4 ... 2 80 0 7 3 3 0 0 0 0
3 33 1 1392 1 3 4 1 1 5 4 ... 3 80 0 8 3 3 8 7 3 0
4 27 2 591 1 2 1 3 1 7 1 ... 4 80 1 6 3 3 2 2 2 2

5 rows × 34 columns

In [32]:
categorical_cols = ['BusinessTravel', 'Department', 'EducationField', 'Gender', 'JobRole', 'MaritalStatus', 'OverTime']
numeric_cols = [col for col in df.columns if col not in categorical_cols]

# Encode categorical columns using label encoding
label_encoder = LabelEncoder()
for col in categorical_cols:
    df[col] = label_encoder.fit_transform(df[col])

# Encode the target variable "Attrition"
df['Attrition'] = label_encoder.fit_transform(df['Attrition'])

# Now, the entire dataset is encoded, including categorical columns and the target variable
X = df.drop(columns=['Attrition'])
y = df['Attrition']
In [33]:
x.head()
Out[33]:
Age BusinessTravel DailyRate Department DistanceFromHome Education EducationField EmployeeCount EmployeeNumber EnvironmentSatisfaction ... RelationshipSatisfaction StandardHours StockOptionLevel TotalWorkingYears TrainingTimesLastYear WorkLifeBalance YearsAtCompany YearsInCurrentRole YearsSinceLastPromotion YearsWithCurrManager
0 41 2 1102 2 1 2 1 1 1 2 ... 1 80 0 8 0 1 6 4 0 5
1 49 1 279 1 8 1 1 1 2 3 ... 4 80 1 10 3 3 10 7 1 7
2 37 2 1373 1 2 2 4 1 4 4 ... 2 80 0 7 3 3 0 0 0 0
3 33 1 1392 1 3 4 1 1 5 4 ... 3 80 0 8 3 3 8 7 3 0
4 27 2 591 1 2 1 3 1 7 1 ... 4 80 1 6 3 3 2 2 2 2

5 rows × 34 columns

In [34]:
y.head()
Out[34]:
0    1
1    0
2    1
3    0
4    0
Name: Attrition, dtype: int32
In [35]:
from sklearn.preprocessing import MinMaxScaler
ms=MinMaxScaler()
In [36]:
X_Scaled=ms.fit_transform(x)
X_Scaled=pd.DataFrame(ms.fit_transform(x),columns=x.columns)
In [37]:
X_Scaled.head()
Out[37]:
Age BusinessTravel DailyRate Department DistanceFromHome Education EducationField EmployeeCount EmployeeNumber EnvironmentSatisfaction ... RelationshipSatisfaction StandardHours StockOptionLevel TotalWorkingYears TrainingTimesLastYear WorkLifeBalance YearsAtCompany YearsInCurrentRole YearsSinceLastPromotion YearsWithCurrManager
0 0.547619 1.0 0.715820 1.0 0.000000 0.25 0.2 0.0 0.000000 0.333333 ... 0.000000 0.0 0.000000 0.200 0.0 0.000000 0.15 0.222222 0.000000 0.294118
1 0.738095 0.5 0.126700 0.5 0.250000 0.00 0.2 0.0 0.000484 0.666667 ... 1.000000 0.0 0.333333 0.250 0.5 0.666667 0.25 0.388889 0.066667 0.411765
2 0.452381 1.0 0.909807 0.5 0.035714 0.25 0.8 0.0 0.001451 1.000000 ... 0.333333 0.0 0.000000 0.175 0.5 0.666667 0.00 0.000000 0.000000 0.000000
3 0.357143 0.5 0.923407 0.5 0.071429 0.75 0.2 0.0 0.001935 1.000000 ... 0.666667 0.0 0.000000 0.200 0.5 0.666667 0.20 0.388889 0.200000 0.000000
4 0.214286 1.0 0.350036 0.5 0.035714 0.00 0.6 0.0 0.002903 0.000000 ... 1.000000 0.0 0.333333 0.150 0.5 0.666667 0.05 0.111111 0.133333 0.117647

5 rows × 34 columns

In [38]:
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test = train_test_split(X_Scaled,y,test_size =0.2,random_state =0)
In [39]:
print(x_train.shape,x_test.shape,y_train.shape,y_test.shape)

(1176, 34) (294, 34) (1176,) (294,)

Logistic Regression¶

In [40]:
from sklearn.linear_model import LogisticRegression
model=LogisticRegression()
In [41]:
model.fit(x_train,y_train)
Out[41]:
LogisticRegression()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
LogisticRegression()
In [42]:
pred=model.predict(x_test)
pred
Out[42]:
array([0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0,
       1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 1, 0, 0])
In [43]:
y_test
Out[43]:
442     0
1091    0
981     1
785     0
1332    1
       ..
1439    0
481     0
124     1
198     0
1229    0
Name: Attrition, Length: 294, dtype: int32
In [44]:
df
Out[44]:
Age Attrition BusinessTravel DailyRate Department DistanceFromHome Education EducationField EmployeeCount EmployeeNumber ... RelationshipSatisfaction StandardHours StockOptionLevel TotalWorkingYears TrainingTimesLastYear WorkLifeBalance YearsAtCompany YearsInCurrentRole YearsSinceLastPromotion YearsWithCurrManager
0 41 1 2 1102 2 1 2 1 1 1 ... 1 80 0 8 0 1 6 4 0 5
1 49 0 1 279 1 8 1 1 1 2 ... 4 80 1 10 3 3 10 7 1 7
2 37 1 2 1373 1 2 2 4 1 4 ... 2 80 0 7 3 3 0 0 0 0
3 33 0 1 1392 1 3 4 1 1 5 ... 3 80 0 8 3 3 8 7 3 0
4 27 0 2 591 1 2 1 3 1 7 ... 4 80 1 6 3 3 2 2 2 2
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
1465 36 0 1 884 1 23 2 3 1 2061 ... 3 80 1 17 3 3 5 2 0 3
1466 39 0 2 613 1 6 1 3 1 2062 ... 1 80 1 9 5 3 7 7 1 7
1467 27 0 2 155 1 4 3 1 1 2064 ... 2 80 1 6 0 3 6 2 0 3
1468 49 0 1 1023 2 2 3 3 1 2065 ... 4 80 0 17 3 2 9 6 0 8
1469 34 0 2 628 1 8 3 3 1 2068 ... 1 80 0 6 3 4 4 3 1 2

1470 rows × 35 columns

In [45]:
x.head()
Out[45]:
Age BusinessTravel DailyRate Department DistanceFromHome Education EducationField EmployeeCount EmployeeNumber EnvironmentSatisfaction ... RelationshipSatisfaction StandardHours StockOptionLevel TotalWorkingYears TrainingTimesLastYear WorkLifeBalance YearsAtCompany YearsInCurrentRole YearsSinceLastPromotion YearsWithCurrManager
0 41 2 1102 2 1 2 1 1 1 2 ... 1 80 0 8 0 1 6 4 0 5
1 49 1 279 1 8 1 1 1 2 3 ... 4 80 1 10 3 3 10 7 1 7
2 37 2 1373 1 2 2 4 1 4 4 ... 2 80 0 7 3 3 0 0 0 0
3 33 1 1392 1 3 4 1 1 5 4 ... 3 80 0 8 3 3 8 7 3 0
4 27 2 591 1 2 1 3 1 7 1 ... 4 80 1 6 3 3 2 2 2 2

5 rows × 34 columns

In [46]:
model.predict(ms.transform([[ 41,2,1102,2,1,2,1,1,1,2,0,94,3,2,7,4,2,5993,19479,8,0,1,11,3,1,80,0,8,0,1,6,4,0,5]]))

C:\Users\Manu\OneDrive\Documents\Anaconda\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but MinMaxScaler was fitted with feature names
  warnings.warn(
C:\Users\Manu\OneDrive\Documents\Anaconda\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names
  warnings.warn(
Out[46]:
array([1])
In [47]:
from sklearn.metrics import accuracy_score,confusion_matrix,classification_report,roc_auc_score,roc_curve
In [48]:
accuracy_score(y_test,pred)
Out[48]:
0.8843537414965986
In [49]:
confusion_matrix(y_test,pred)
Out[49]:
array([[242,   3],
       [ 31,  18]], dtype=int64)
In [50]:
pd.crosstab(y_test,pred)
Out[50]:
col_0 0 1
Attrition
0 242 3
1 31 18
In [51]:
a1=(242+18)/294 #accuracy
a1
Out[51]:
0.8843537414965986
In [52]:
r=18/(18+31) #recall
r
Out[52]:
0.3673469387755102
In [53]:
p=18/(3+18) #precision
p
Out[53]:
0.8571428571428571
In [54]:
f1=2*p*r/(p+r) #F1 score
f1
Out[54]:
0.5142857142857143
In [55]:
print(classification_report(y_test,pred))

              precision    recall  f1-score   support

           0       0.89      0.99      0.93       245
           1       0.86      0.37      0.51        49

    accuracy                           0.88       294
   macro avg       0.87      0.68      0.72       294
weighted avg       0.88      0.88      0.86       294
In [56]:
probability=model.predict_proba(x_test)[:,1]
In [57]:
probability
Out[57]:
array([0.16000127, 0.20600667, 0.31532384, 0.09242886, 0.63667551,
       0.06153061, 0.61819432, 0.0757087 , 0.00841372, 0.3912069 ,
       0.05398439, 0.33293123, 0.02020698, 0.67215483, 0.19786547,
       0.03454902, 0.11043981, 0.17101703, 0.04477777, 0.22783614,
       0.2335018 , 0.01553905, 0.06464492, 0.05029956, 0.58792413,
       0.44849464, 0.07412714, 0.04460935, 0.67666632, 0.0584383 ,
       0.01599026, 0.03521098, 0.06963085, 0.17397462, 0.07830857,
       0.04288032, 0.08150424, 0.07106342, 0.03622137, 0.05223965,
       0.04862098, 0.02091497, 0.01819361, 0.01362467, 0.02873997,
       0.50236969, 0.41553218, 0.00306874, 0.73976412, 0.51382382,
       0.09637213, 0.48845516, 0.08036228, 0.25757243, 0.66516772,
       0.26308027, 0.01964858, 0.30198497, 0.02919946, 0.16038964,
       0.02102747, 0.21670232, 0.13981568, 0.0358316 , 0.37208403,
       0.03002317, 0.29091186, 0.16041142, 0.10437497, 0.08695177,
       0.08217589, 0.30984518, 0.08531362, 0.07420689, 0.12268651,
       0.06192552, 0.04640904, 0.07624712, 0.19738483, 0.03236316,
       0.00884439, 0.0244108 , 0.13635803, 0.0260104 , 0.03341008,
       0.08186888, 0.00499397, 0.03474852, 0.03858027, 0.14602694,
       0.26167665, 0.16667357, 0.27400109, 0.24159565, 0.02160421,
       0.17748606, 0.34076078, 0.28022482, 0.06914126, 0.05003806,
       0.24437761, 0.74698271, 0.35438567, 0.01920627, 0.08778845,
       0.03255847, 0.05461351, 0.15123251, 0.06843702, 0.13752637,
       0.09584388, 0.04669882, 0.02493091, 0.15383171, 0.07081259,
       0.03089296, 0.0537667 , 0.11554316, 0.00881616, 0.01263271,
       0.17552253, 0.05045234, 0.08823238, 0.82995757, 0.03017756,
       0.0236819 , 0.0087012 , 0.1349589 , 0.16474801, 0.05202613,
       0.01524549, 0.29278083, 0.54767448, 0.34275448, 0.04629541,
       0.38966344, 0.61333366, 0.14552367, 0.07402366, 0.24143471,
       0.09418418, 0.0689069 , 0.10061956, 0.19346327, 0.20026293,
       0.03004939, 0.14900424, 0.00348846, 0.11225149, 0.15843155,
       0.06047573, 0.18601882, 0.06085869, 0.12221317, 0.03280184,
       0.02738799, 0.06356425, 0.08302382, 0.01541716, 0.014665  ,
       0.38517822, 0.01264231, 0.14961974, 0.80508787, 0.11598661,
       0.2842811 , 0.17020143, 0.1530583 , 0.02764153, 0.00613226,
       0.04191632, 0.09782393, 0.11551417, 0.10377982, 0.01779313,
       0.14371315, 0.10615435, 0.10298963, 0.05132621, 0.09061081,
       0.02897383, 0.09924087, 0.00512032, 0.75108423, 0.04296968,
       0.04062134, 0.37518972, 0.04563128, 0.7251816 , 0.10671665,
       0.36949086, 0.38146941, 0.32095493, 0.05266802, 0.08172004,
       0.13947833, 0.04334317, 0.01469593, 0.26413988, 0.06330966,
       0.1614747 , 0.15380517, 0.67152357, 0.05840793, 0.27891823,
       0.04512564, 0.46033865, 0.00348431, 0.14068967, 0.02747401,
       0.12714133, 0.17284246, 0.07341066, 0.10099827, 0.16870885,
       0.02560842, 0.01824031, 0.08670796, 0.02834237, 0.13710215,
       0.08778935, 0.2200061 , 0.73401148, 0.15938978, 0.4095449 ,
       0.01513845, 0.11306309, 0.21497506, 0.32337575, 0.03409266,
       0.04256318, 0.32157531, 0.05454465, 0.02348479, 0.16423352,
       0.32696147, 0.22892063, 0.00877159, 0.08198819, 0.01156361,
       0.1408691 , 0.29235147, 0.01270305, 0.17329916, 0.04081391,
       0.04094165, 0.42771425, 0.34958286, 0.03766772, 0.12025286,
       0.37698923, 0.3192629 , 0.79559338, 0.05385659, 0.21597037,
       0.06383728, 0.00570991, 0.66018187, 0.35855286, 0.37783606,
       0.36781398, 0.03554512, 0.21718203, 0.05943622, 0.06554485,
       0.10081475, 0.00818713, 0.26591316, 0.42809675, 0.06542835,
       0.09296803, 0.01259826, 0.14226651, 0.05072662, 0.02372258,
       0.02586923, 0.06760427, 0.24315648, 0.26961432, 0.19831733,
       0.2652296 , 0.0165923 , 0.15784236, 0.08398982, 0.02711775,
       0.18750547, 0.00783535, 0.2844239 , 0.00270742, 0.02484969,
       0.22585745, 0.72775605, 0.07691547, 0.26304359])
In [58]:
fpr,tpr,threshsholds = roc_curve(y_test,probability)
In [59]:
plt.plot(fpr,tpr)
plt.xlabel('FPR')
plt.ylabel('TPR')
plt.title('ROC CURVE')
plt.show()

DecisionTree¶

In [60]:
from sklearn.tree import DecisionTreeClassifier
dtc=DecisionTreeClassifier()
In [61]:
dtc.fit(x_train,y_train)
Out[61]:
DecisionTreeClassifier()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
DecisionTreeClassifier()
In [62]:
pred=dtc.predict(x_test)
pred
Out[62]:
array([0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0,
       0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0,
       0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1,
       0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1,
       1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0,
       0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,
       0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 1,
       0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,
       0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 0, 1,
       0, 0, 1, 0, 0, 0, 0, 0])
In [63]:
y_test
Out[63]:
442     0
1091    0
981     1
785     0
1332    1
       ..
1439    0
481     0
124     1
198     0
1229    0
Name: Attrition, Length: 294, dtype: int32
In [64]:
df
Out[64]:
Age Attrition BusinessTravel DailyRate Department DistanceFromHome Education EducationField EmployeeCount EmployeeNumber ... RelationshipSatisfaction StandardHours StockOptionLevel TotalWorkingYears TrainingTimesLastYear WorkLifeBalance YearsAtCompany YearsInCurrentRole YearsSinceLastPromotion YearsWithCurrManager
0 41 1 2 1102 2 1 2 1 1 1 ... 1 80 0 8 0 1 6 4 0 5
1 49 0 1 279 1 8 1 1 1 2 ... 4 80 1 10 3 3 10 7 1 7
2 37 1 2 1373 1 2 2 4 1 4 ... 2 80 0 7 3 3 0 0 0 0
3 33 0 1 1392 1 3 4 1 1 5 ... 3 80 0 8 3 3 8 7 3 0
4 27 0 2 591 1 2 1 3 1 7 ... 4 80 1 6 3 3 2 2 2 2
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
1465 36 0 1 884 1 23 2 3 1 2061 ... 3 80 1 17 3 3 5 2 0 3
1466 39 0 2 613 1 6 1 3 1 2062 ... 1 80 1 9 5 3 7 7 1 7
1467 27 0 2 155 1 4 3 1 1 2064 ... 2 80 1 6 0 3 6 2 0 3
1468 49 0 1 1023 2 2 3 3 1 2065 ... 4 80 0 17 3 2 9 6 0 8
1469 34 0 2 628 1 8 3 3 1 2068 ... 1 80 0 6 3 4 4 3 1 2

1470 rows × 35 columns

In [65]:
dtc.predict(ms.transform([[41,2,1102,2,1,2,1,1,1,2,0,94,3,2,7,4,2,5993,19479,8,0,1,11,3,1,80,0,8,0,1,6,4,0,5]]))

C:\Users\Manu\OneDrive\Documents\Anaconda\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but MinMaxScaler was fitted with feature names
  warnings.warn(
C:\Users\Manu\OneDrive\Documents\Anaconda\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but DecisionTreeClassifier was fitted with feature names
  warnings.warn(
Out[65]:
array([1])
In [66]:
from sklearn.metrics import accuracy_score,confusion_matrix,classification_report,roc_auc_score,roc_curve
In [67]:
accuracy_score(y_test,pred)
Out[67]:
0.7517006802721088
In [68]:
confusion_matrix(y_test,pred)
Out[68]:
array([[205,  40],
       [ 33,  16]], dtype=int64)
In [69]:
pd.crosstab(y_test,pred)
Out[69]:
col_0 0 1
Attrition
0 205 40
1 33 16
In [70]:
a2 = (209+18)/294 #accuarcy
a2
Out[70]:
0.7721088435374149
In [71]:
r2 = 18/(31+18) #recall
r2
Out[71]:
0.3673469387755102
In [72]:
p2 = 18/(36+18) #precision
p2
Out[72]:
0.3333333333333333
In [73]:
f2 = 2*p2*r2/(p2+r2) # F1 score
f2
Out[73]:
0.34951456310679613
In [74]:
print(classification_report(y_test,pred))

              precision    recall  f1-score   support

           0       0.86      0.84      0.85       245
           1       0.29      0.33      0.30        49

    accuracy                           0.75       294
   macro avg       0.57      0.58      0.58       294
weighted avg       0.77      0.75      0.76       294
In [75]:
probability=dtc.predict_proba(x_test)[:,1]
In [76]:
probability
Out[76]:
array([0., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0., 0., 0., 1., 0., 0., 0.,
       0., 0., 1., 1., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0., 0.,
       0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 1.,
       1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 1., 0., 0., 0.,
       0., 0., 0., 1., 0., 1., 0., 1., 1., 0., 0., 0., 1., 0., 0., 0., 0.,
       0., 1., 1., 0., 0., 1., 0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0.,
       1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
       0., 0., 0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 1., 1., 1., 1., 0.,
       0., 0., 1., 0., 0., 0., 1., 0., 0., 0., 0., 1., 0., 0., 0., 1., 0.,
       0., 0., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
       0., 0., 0., 0., 0., 1., 0., 1., 1., 0., 0., 0., 0., 1., 0., 0., 1.,
       0., 0., 1., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 0.,
       1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 1., 1., 0.,
       0., 1., 0., 0., 0., 0., 1., 1., 0., 0., 1., 0., 0., 0., 0., 0., 0.,
       0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
       0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 1., 0., 1., 0., 0., 0., 0.,
       0., 0., 0., 0., 0., 0., 0., 1., 0., 0., 1., 1., 0., 1., 0., 0., 1.,
       0., 0., 0., 0., 0.])
In [77]:
fpr,tpr,threshsholds = roc_curve(y_test,probability)
In [78]:
plt.plot(fpr,tpr)
plt.xlabel('FPR')
plt.ylabel('TPR')
plt.title('ROC CURVE')
plt.show()
In [79]:
from sklearn import tree
plt.figure(figsize=(25,15))
tree.plot_tree(dtc,filled=True)
Out[79]:
[Text(0.322017553667263, 0.9722222222222222, 'x[27] <= 0.038\ngini = 0.269\nsamples = 1176\nvalue = [988, 188]'),
 Text(0.07871198568872988, 0.9166666666666666, 'x[16] <= 0.75\ngini = 0.5\nsamples = 78\nvalue = [39, 39]'),
 Text(0.046511627906976744, 0.8611111111111112, 'x[4] <= 0.554\ngini = 0.426\nsamples = 39\nvalue = [27, 12]'),
 Text(0.028622540250447227, 0.8055555555555556, 'x[15] <= 0.167\ngini = 0.312\nsamples = 31\nvalue = [25, 6]'),
 Text(0.014311270125223614, 0.75, 'x[9] <= 0.5\ngini = 0.49\nsamples = 7\nvalue = [3, 4]'),
 Text(0.007155635062611807, 0.6944444444444444, 'gini = 0.0\nsamples = 3\nvalue = [0, 3]'),
 Text(0.02146690518783542, 0.6944444444444444, 'x[4] <= 0.143\ngini = 0.375\nsamples = 4\nvalue = [3, 1]'),
 Text(0.014311270125223614, 0.6388888888888888, 'gini = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(0.028622540250447227, 0.6388888888888888, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.04293381037567084, 0.75, 'x[19] <= 0.056\ngini = 0.153\nsamples = 24\nvalue = [22, 2]'),
 Text(0.03577817531305903, 0.6944444444444444, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.05008944543828265, 0.6944444444444444, 'x[9] <= 0.167\ngini = 0.083\nsamples = 23\nvalue = [22, 1]'),
 Text(0.04293381037567084, 0.6388888888888888, 'x[23] <= 0.5\ngini = 0.5\nsamples = 2\nvalue = [1, 1]'),
 Text(0.03577817531305903, 0.5833333333333334, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.05008944543828265, 0.5833333333333334, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.057245080500894455, 0.6388888888888888, 'gini = 0.0\nsamples = 21\nvalue = [21, 0]'),
 Text(0.06440071556350627, 0.8055555555555556, 'x[22] <= 0.679\ngini = 0.375\nsamples = 8\nvalue = [2, 6]'),
 Text(0.057245080500894455, 0.75, 'gini = 0.0\nsamples = 6\nvalue = [0, 6]'),
 Text(0.07155635062611806, 0.75, 'gini = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(0.11091234347048301, 0.8611111111111112, 'x[11] <= 0.364\ngini = 0.426\nsamples = 39\nvalue = [12, 27]'),
 Text(0.09302325581395349, 0.8055555555555556, 'x[0] <= 0.369\ngini = 0.133\nsamples = 14\nvalue = [1, 13]'),
 Text(0.08586762075134168, 0.75, 'gini = 0.0\nsamples = 13\nvalue = [0, 13]'),
 Text(0.1001788908765653, 0.75, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.12880143112701253, 0.8055555555555556, 'x[8] <= 0.105\ngini = 0.493\nsamples = 25\nvalue = [11, 14]'),
 Text(0.11449016100178891, 0.75, 'x[1] <= 0.75\ngini = 0.278\nsamples = 6\nvalue = [5, 1]'),
 Text(0.1073345259391771, 0.6944444444444444, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.12164579606440072, 0.6944444444444444, 'gini = 0.0\nsamples = 5\nvalue = [5, 0]'),
 Text(0.14311270125223613, 0.75, 'x[15] <= 0.5\ngini = 0.432\nsamples = 19\nvalue = [6, 13]'),
 Text(0.13595706618962433, 0.6944444444444444, 'gini = 0.0\nsamples = 7\nvalue = [0, 7]'),
 Text(0.15026833631484796, 0.6944444444444444, 'x[6] <= 0.4\ngini = 0.5\nsamples = 12\nvalue = [6, 6]'),
 Text(0.13595706618962433, 0.6388888888888888, 'x[32] <= 0.033\ngini = 0.278\nsamples = 6\nvalue = [5, 1]'),
 Text(0.12880143112701253, 0.5833333333333334, 'gini = 0.0\nsamples = 5\nvalue = [5, 0]'),
 Text(0.14311270125223613, 0.5833333333333334, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.16457960644007155, 0.6388888888888888, 'x[8] <= 0.249\ngini = 0.278\nsamples = 6\nvalue = [1, 5]'),
 Text(0.15742397137745975, 0.5833333333333334, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.17173524150268335, 0.5833333333333334, 'gini = 0.0\nsamples = 5\nvalue = [0, 5]'),
 Text(0.565323121645796, 0.9166666666666666, 'x[21] <= 0.5\ngini = 0.235\nsamples = 1098\nvalue = [949, 149]'),
 Text(0.31937611806797855, 0.8611111111111112, 'x[29] <= 0.167\ngini = 0.162\nsamples = 798\nvalue = [727, 71]'),
 Text(0.18604651162790697, 0.8055555555555556, 'x[8] <= 0.445\ngini = 0.38\nsamples = 47\nvalue = [35, 12]'),
 Text(0.17173524150268335, 0.75, 'x[16] <= 0.75\ngini = 0.1\nsamples = 19\nvalue = [18, 1]'),
 Text(0.16457960644007155, 0.6944444444444444, 'gini = 0.0\nsamples = 18\nvalue = [18, 0]'),
 Text(0.17889087656529518, 0.6944444444444444, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.2003577817531306, 0.75, 'x[17] <= 0.094\ngini = 0.477\nsamples = 28\nvalue = [17, 11]'),
 Text(0.19320214669051877, 0.6944444444444444, 'gini = 0.0\nsamples = 4\nvalue = [0, 4]'),
 Text(0.2075134168157424, 0.6944444444444444, 'x[32] <= 0.6\ngini = 0.413\nsamples = 24\nvalue = [17, 7]'),
 Text(0.2003577817531306, 0.6388888888888888, 'x[11] <= 0.486\ngini = 0.351\nsamples = 22\nvalue = [17, 5]'),
 Text(0.19320214669051877, 0.5833333333333334, 'x[24] <= 0.5\ngini = 0.496\nsamples = 11\nvalue = [6, 5]'),
 Text(0.18604651162790697, 0.5277777777777778, 'x[4] <= 0.036\ngini = 0.408\nsamples = 7\nvalue = [2, 5]'),
 Text(0.17889087656529518, 0.4722222222222222, 'gini = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(0.19320214669051877, 0.4722222222222222, 'gini = 0.0\nsamples = 5\nvalue = [0, 5]'),
 Text(0.2003577817531306, 0.5277777777777778, 'gini = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(0.2075134168157424, 0.5833333333333334, 'gini = 0.0\nsamples = 11\nvalue = [11, 0]'),
 Text(0.2146690518783542, 0.6388888888888888, 'gini = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(0.4527057245080501, 0.8055555555555556, 'x[30] <= 0.963\ngini = 0.145\nsamples = 751\nvalue = [692, 59]'),
 Text(0.4455500894454383, 0.75, 'x[30] <= 0.113\ngini = 0.143\nsamples = 750\nvalue = [692, 58]'),
 Text(0.31440071556350624, 0.6944444444444444, 'x[9] <= 0.167\ngini = 0.218\nsamples = 257\nvalue = [225, 32]'),
 Text(0.2701252236135957, 0.6388888888888888, 'x[33] <= 0.147\ngini = 0.355\nsamples = 65\nvalue = [50, 15]'),
 Text(0.24686940966010734, 0.5833333333333334, 'x[33] <= 0.029\ngini = 0.303\nsamples = 59\nvalue = [48, 11]'),
 Text(0.22182468694096602, 0.5277777777777778, 'x[12] <= 0.5\ngini = 0.463\nsamples = 22\nvalue = [14, 8]'),
 Text(0.2075134168157424, 0.4722222222222222, 'x[11] <= 0.179\ngini = 0.198\nsamples = 9\nvalue = [8, 1]'),
 Text(0.2003577817531306, 0.4166666666666667, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.2146690518783542, 0.4166666666666667, 'gini = 0.0\nsamples = 8\nvalue = [8, 0]'),
 Text(0.23613595706618962, 0.4722222222222222, 'x[11] <= 0.4\ngini = 0.497\nsamples = 13\nvalue = [6, 7]'),
 Text(0.22898032200357782, 0.4166666666666667, 'gini = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(0.24329159212880144, 0.4166666666666667, 'x[4] <= 0.286\ngini = 0.346\nsamples = 9\nvalue = [2, 7]'),
 Text(0.23613595706618962, 0.3611111111111111, 'x[2] <= 0.369\ngini = 0.444\nsamples = 3\nvalue = [2, 1]'),
 Text(0.22898032200357782, 0.3055555555555556, 'gini = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(0.24329159212880144, 0.3055555555555556, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.2504472271914132, 0.3611111111111111, 'gini = 0.0\nsamples = 6\nvalue = [0, 6]'),
 Text(0.27191413237924866, 0.5277777777777778, 'x[15] <= 0.167\ngini = 0.149\nsamples = 37\nvalue = [34, 3]'),
 Text(0.26475849731663686, 0.4722222222222222, 'x[29] <= 0.5\ngini = 0.5\nsamples = 6\nvalue = [3, 3]'),
 Text(0.25760286225402507, 0.4166666666666667, 'gini = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(0.27191413237924866, 0.4166666666666667, 'gini = 0.0\nsamples = 3\nvalue = [0, 3]'),
 Text(0.27906976744186046, 0.4722222222222222, 'gini = 0.0\nsamples = 31\nvalue = [31, 0]'),
 Text(0.29338103756708406, 0.5833333333333334, 'x[8] <= 0.065\ngini = 0.444\nsamples = 6\nvalue = [2, 4]'),
 Text(0.28622540250447226, 0.5277777777777778, 'gini = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(0.3005366726296959, 0.5277777777777778, 'gini = 0.0\nsamples = 4\nvalue = [0, 4]'),
 Text(0.35867620751341683, 0.6388888888888888, 'x[0] <= 0.321\ngini = 0.161\nsamples = 192\nvalue = [175, 17]'),
 Text(0.3220035778175313, 0.5833333333333334, 'x[6] <= 0.1\ngini = 0.294\nsamples = 67\nvalue = [55, 12]'),
 Text(0.3148479427549195, 0.5277777777777778, 'gini = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(0.3291592128801431, 0.5277777777777778, 'x[29] <= 0.5\ngini = 0.26\nsamples = 65\nvalue = [55, 10]'),
 Text(0.3112701252236136, 0.4722222222222222, 'x[11] <= 0.679\ngini = 0.469\nsamples = 16\nvalue = [10, 6]'),
 Text(0.3041144901610018, 0.4166666666666667, 'x[4] <= 0.018\ngini = 0.444\nsamples = 9\nvalue = [3, 6]'),
 Text(0.29695885509839, 0.3611111111111111, 'gini = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(0.3112701252236136, 0.3611111111111111, 'x[6] <= 0.4\ngini = 0.245\nsamples = 7\nvalue = [1, 6]'),
 Text(0.3041144901610018, 0.3055555555555556, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.3184257602862254, 0.3055555555555556, 'gini = 0.0\nsamples = 6\nvalue = [0, 6]'),
 Text(0.3184257602862254, 0.4166666666666667, 'gini = 0.0\nsamples = 7\nvalue = [7, 0]'),
 Text(0.3470483005366726, 0.4722222222222222, 'x[2] <= 0.037\ngini = 0.15\nsamples = 49\nvalue = [45, 4]'),
 Text(0.33989266547406083, 0.4166666666666667, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.3542039355992844, 0.4166666666666667, 'x[2] <= 0.938\ngini = 0.117\nsamples = 48\nvalue = [45, 3]'),
 Text(0.3470483005366726, 0.3611111111111111, 'x[5] <= 0.875\ngini = 0.081\nsamples = 47\nvalue = [45, 2]'),
 Text(0.33273703041144903, 0.3055555555555556, 'x[12] <= 0.167\ngini = 0.043\nsamples = 45\nvalue = [44, 1]'),
 Text(0.32558139534883723, 0.25, 'x[22] <= 0.214\ngini = 0.444\nsamples = 3\nvalue = [2, 1]'),
 Text(0.3184257602862254, 0.19444444444444445, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.33273703041144903, 0.19444444444444445, 'gini = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(0.33989266547406083, 0.25, 'gini = 0.0\nsamples = 42\nvalue = [42, 0]'),
 Text(0.3613595706618962, 0.3055555555555556, 'x[6] <= 0.9\ngini = 0.5\nsamples = 2\nvalue = [1, 1]'),
 Text(0.3542039355992844, 0.25, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.3685152057245081, 0.25, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.3613595706618962, 0.3611111111111111, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.3953488372093023, 0.5833333333333334, 'x[8] <= 0.022\ngini = 0.077\nsamples = 125\nvalue = [120, 5]'),
 Text(0.3756708407871199, 0.5277777777777778, 'x[27] <= 0.188\ngini = 0.5\nsamples = 4\nvalue = [2, 2]'),
 Text(0.3685152057245081, 0.4722222222222222, 'gini = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(0.3828264758497317, 0.4722222222222222, 'gini = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(0.4150268336314848, 0.5277777777777778, 'x[18] <= 0.968\ngini = 0.048\nsamples = 121\nvalue = [118, 3]'),
 Text(0.39713774597495527, 0.4722222222222222, 'x[2] <= 0.98\ngini = 0.033\nsamples = 118\nvalue = [116, 2]'),
 Text(0.3828264758497317, 0.4166666666666667, 'x[14] <= 0.938\ngini = 0.017\nsamples = 114\nvalue = [113, 1]'),
 Text(0.3756708407871199, 0.3611111111111111, 'gini = 0.0\nsamples = 107\nvalue = [107, 0]'),
 Text(0.38998211091234347, 0.3611111111111111, 'x[16] <= 0.25\ngini = 0.245\nsamples = 7\nvalue = [6, 1]'),
 Text(0.3828264758497317, 0.3055555555555556, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.39713774597495527, 0.3055555555555556, 'gini = 0.0\nsamples = 6\nvalue = [6, 0]'),
 Text(0.41144901610017887, 0.4166666666666667, 'x[12] <= 0.833\ngini = 0.375\nsamples = 4\nvalue = [3, 1]'),
 Text(0.40429338103756707, 0.3611111111111111, 'gini = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(0.4186046511627907, 0.3611111111111111, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.4329159212880143, 0.4722222222222222, 'x[27] <= 0.15\ngini = 0.444\nsamples = 3\nvalue = [2, 1]'),
 Text(0.4257602862254025, 0.4166666666666667, 'gini = 0.0\nsamples = 2\nvalue = [2, 0]'),
 Text(0.4400715563506261, 0.4166666666666667, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.5766994633273703, 0.6944444444444444, 'x[30] <= 0.787\ngini = 0.1\nsamples = 493\nvalue = [467, 26]'),
 Text(0.5398032200357782, 0.6388888888888888, 'x[15] <= 0.5\ngini = 0.094\nsamples = 486\nvalue = [462, 24]'),
 Text(0.4874776386404293, 0.5833333333333334, 'x[14] <= 0.938\ngini = 0.154\nsamples = 191\nvalue = [175, 16]'),
 Text(0.4803220035778175, 0.5277777777777778, 'x[18] <= 0.481\ngini = 0.145\nsamples = 190\nvalue = [175, 15]'),
 Text(0.46153846153846156, 0.4722222222222222, 'x[33] <= 0.794\ngini = 0.221\nsamples = 95\nvalue = [83, 12]'),
 Text(0.4543828264758497, 0.4166666666666667, 'x[18] <= 0.47\ngini = 0.207\nsamples = 94\nvalue = [83, 11]'),
 Text(0.4472271914132379, 0.3611111111111111, 'x[5] <= 0.375\ngini = 0.192\nsamples = 93\nvalue = [83, 10]'),
 Text(0.42397137745974955, 0.3055555555555556, 'x[6] <= 0.9\ngini = 0.363\nsamples = 21\nvalue = [16, 5]'),
 Text(0.41681574239713776, 0.25, 'x[17] <= 0.413\ngini = 0.266\nsamples = 19\nvalue = [16, 3]'),
 Text(0.40250447227191416, 0.19444444444444445, 'x[19] <= 0.056\ngini = 0.117\nsamples = 16\nvalue = [15, 1]'),
 Text(0.3953488372093023, 0.1388888888888889, 'x[22] <= 0.107\ngini = 0.5\nsamples = 2\nvalue = [1, 1]'),
 Text(0.3881932021466905, 0.08333333333333333, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.40250447227191416, 0.08333333333333333, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.40966010733452596, 0.1388888888888889, 'gini = 0.0\nsamples = 14\nvalue = [14, 0]'),
 Text(0.43112701252236135, 0.19444444444444445, 'x[14] <= 0.5\ngini = 0.444\nsamples = 3\nvalue = [1, 2]'),
 Text(0.42397137745974955, 0.1388888888888889, 'gini = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(0.43828264758497315, 0.1388888888888889, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.43112701252236135, 0.25, 'gini = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(0.47048300536672627, 0.3055555555555556, 'x[31] <= 0.139\ngini = 0.129\nsamples = 72\nvalue = [67, 5]'),
 Text(0.4525939177101968, 0.25, 'x[8] <= 0.68\ngini = 0.444\nsamples = 6\nvalue = [4, 2]'),
 Text(0.44543828264758495, 0.19444444444444445, 'gini = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(0.4597495527728086, 0.19444444444444445, 'gini = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(0.4883720930232558, 0.25, 'x[2] <= 0.958\ngini = 0.087\nsamples = 66\nvalue = [63, 3]'),
 Text(0.4740608228980322, 0.19444444444444445, 'x[28] <= 0.583\ngini = 0.061\nsamples = 64\nvalue = [62, 2]'),
 Text(0.4669051878354204, 0.1388888888888889, 'gini = 0.0\nsamples = 52\nvalue = [52, 0]'),
 Text(0.481216457960644, 0.1388888888888889, 'x[3] <= 0.75\ngini = 0.278\nsamples = 12\nvalue = [10, 2]'),
 Text(0.4740608228980322, 0.08333333333333333, 'gini = 0.0\nsamples = 9\nvalue = [9, 0]'),
 Text(0.4883720930232558, 0.08333333333333333, 'x[9] <= 0.5\ngini = 0.444\nsamples = 3\nvalue = [1, 2]'),
 Text(0.481216457960644, 0.027777777777777776, 'gini = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(0.49552772808586765, 0.027777777777777776, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.5026833631484794, 0.19444444444444445, 'x[30] <= 0.35\ngini = 0.5\nsamples = 2\nvalue = [1, 1]'),
 Text(0.49552772808586765, 0.1388888888888889, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.5098389982110912, 0.1388888888888889, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.46153846153846156, 0.3611111111111111, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.46869409660107336, 0.4166666666666667, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.4991055456171735, 0.4722222222222222, 'x[19] <= 0.5\ngini = 0.061\nsamples = 95\nvalue = [92, 3]'),
 Text(0.4919499105545617, 0.4166666666666667, 'gini = 0.0\nsamples = 76\nvalue = [76, 0]'),
 Text(0.5062611806797853, 0.4166666666666667, 'x[33] <= 0.088\ngini = 0.266\nsamples = 19\nvalue = [16, 3]'),
 Text(0.4919499105545617, 0.3611111111111111, 'x[15] <= 0.167\ngini = 0.444\nsamples = 3\nvalue = [1, 2]'),
 Text(0.4847942754919499, 0.3055555555555556, 'gini = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(0.4991055456171735, 0.3055555555555556, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.5205724508050089, 0.3611111111111111, 'x[17] <= 0.108\ngini = 0.117\nsamples = 16\nvalue = [15, 1]'),
 Text(0.5134168157423972, 0.3055555555555556, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.5277280858676208, 0.3055555555555556, 'gini = 0.0\nsamples = 15\nvalue = [15, 0]'),
 Text(0.49463327370304117, 0.5277777777777778, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.592128801431127, 0.5833333333333334, 'x[22] <= 0.036\ngini = 0.053\nsamples = 295\nvalue = [287, 8]'),
 Text(0.5670840787119857, 0.5277777777777778, 'x[32] <= 0.7\ngini = 0.159\nsamples = 46\nvalue = [42, 4]'),
 Text(0.5599284436493739, 0.4722222222222222, 'x[12] <= 0.167\ngini = 0.124\nsamples = 45\nvalue = [42, 3]'),
 Text(0.5420393559928444, 0.4166666666666667, 'x[4] <= 0.054\ngini = 0.5\nsamples = 2\nvalue = [1, 1]'),
 Text(0.5348837209302325, 0.3611111111111111, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.5491949910554562, 0.3611111111111111, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.5778175313059034, 0.4166666666666667, 'x[27] <= 0.688\ngini = 0.089\nsamples = 43\nvalue = [41, 2]'),
 Text(0.5635062611806798, 0.3611111111111111, 'x[14] <= 0.062\ngini = 0.048\nsamples = 41\nvalue = [40, 1]'),
 Text(0.556350626118068, 0.3055555555555556, 'x[9] <= 0.167\ngini = 0.375\nsamples = 4\nvalue = [3, 1]'),
 Text(0.5491949910554562, 0.25, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.5635062611806798, 0.25, 'gini = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(0.5706618962432916, 0.3055555555555556, 'gini = 0.0\nsamples = 37\nvalue = [37, 0]'),
 Text(0.592128801431127, 0.3611111111111111, 'x[9] <= 0.333\ngini = 0.5\nsamples = 2\nvalue = [1, 1]'),
 Text(0.5849731663685152, 0.3055555555555556, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.5992844364937389, 0.3055555555555556, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.5742397137745975, 0.4722222222222222, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.6171735241502684, 0.5277777777777778, 'x[17] <= 0.056\ngini = 0.032\nsamples = 249\nvalue = [245, 4]'),
 Text(0.5992844364937389, 0.4722222222222222, 'x[16] <= 0.75\ngini = 0.32\nsamples = 5\nvalue = [4, 1]'),
 Text(0.592128801431127, 0.4166666666666667, 'gini = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(0.6064400715563506, 0.4166666666666667, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.6350626118067979, 0.4722222222222222, 'x[2] <= 0.015\ngini = 0.024\nsamples = 244\nvalue = [241, 3]'),
 Text(0.6207513416815742, 0.4166666666666667, 'x[4] <= 0.875\ngini = 0.278\nsamples = 6\nvalue = [5, 1]'),
 Text(0.6135957066189625, 0.3611111111111111, 'gini = 0.0\nsamples = 5\nvalue = [5, 0]'),
 Text(0.627906976744186, 0.3611111111111111, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.6493738819320215, 0.4166666666666667, 'x[24] <= 0.167\ngini = 0.017\nsamples = 238\nvalue = [236, 2]'),
 Text(0.6422182468694096, 0.3611111111111111, 'x[29] <= 0.833\ngini = 0.073\nsamples = 53\nvalue = [51, 2]'),
 Text(0.627906976744186, 0.3055555555555556, 'x[33] <= 0.088\ngini = 0.041\nsamples = 48\nvalue = [47, 1]'),
 Text(0.6207513416815742, 0.25, 'x[14] <= 0.312\ngini = 0.245\nsamples = 7\nvalue = [6, 1]'),
 Text(0.6135957066189625, 0.19444444444444445, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.627906976744186, 0.19444444444444445, 'gini = 0.0\nsamples = 6\nvalue = [6, 0]'),
 Text(0.6350626118067979, 0.25, 'gini = 0.0\nsamples = 41\nvalue = [41, 0]'),
 Text(0.6565295169946332, 0.3055555555555556, 'x[0] <= 0.631\ngini = 0.32\nsamples = 5\nvalue = [4, 1]'),
 Text(0.6493738819320215, 0.25, 'gini = 0.0\nsamples = 4\nvalue = [4, 0]'),
 Text(0.6636851520572451, 0.25, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.6565295169946332, 0.3611111111111111, 'gini = 0.0\nsamples = 185\nvalue = [185, 0]'),
 Text(0.6135957066189625, 0.6388888888888888, 'x[10] <= 0.5\ngini = 0.408\nsamples = 7\nvalue = [5, 2]'),
 Text(0.6064400715563506, 0.5833333333333334, 'gini = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(0.6207513416815742, 0.5833333333333334, 'gini = 0.0\nsamples = 5\nvalue = [5, 0]'),
 Text(0.4598613595706619, 0.75, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.8112701252236136, 0.8611111111111112, 'x[17] <= 0.157\ngini = 0.385\nsamples = 300\nvalue = [222, 78]'),
 Text(0.7182468694096601, 0.8055555555555556, 'x[26] <= 0.167\ngini = 0.5\nsamples = 96\nvalue = [49, 47]'),
 Text(0.6815742397137746, 0.75, 'x[4] <= 0.161\ngini = 0.459\nsamples = 42\nvalue = [15, 27]'),
 Text(0.6565295169946332, 0.6944444444444444, 'x[8] <= 0.415\ngini = 0.499\nsamples = 23\nvalue = [12, 11]'),
 Text(0.6422182468694096, 0.6388888888888888, 'x[18] <= 0.561\ngini = 0.355\nsamples = 13\nvalue = [3, 10]'),
 Text(0.6350626118067979, 0.5833333333333334, 'gini = 0.0\nsamples = 8\nvalue = [0, 8]'),
 Text(0.6493738819320215, 0.5833333333333334, 'x[9] <= 0.333\ngini = 0.48\nsamples = 5\nvalue = [3, 2]'),
 Text(0.6422182468694096, 0.5277777777777778, 'gini = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(0.6565295169946332, 0.5277777777777778, 'gini = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(0.6708407871198568, 0.6388888888888888, 'x[3] <= 0.75\ngini = 0.18\nsamples = 10\nvalue = [9, 1]'),
 Text(0.6636851520572451, 0.5833333333333334, 'gini = 0.0\nsamples = 8\nvalue = [8, 0]'),
 Text(0.6779964221824687, 0.5833333333333334, 'x[22] <= 0.357\ngini = 0.5\nsamples = 2\nvalue = [1, 1]'),
 Text(0.6708407871198568, 0.5277777777777778, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.6851520572450805, 0.5277777777777778, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.7066189624329159, 0.6944444444444444, 'x[11] <= 0.2\ngini = 0.266\nsamples = 19\nvalue = [3, 16]'),
 Text(0.6994633273703041, 0.6388888888888888, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.7137745974955277, 0.6388888888888888, 'x[27] <= 0.35\ngini = 0.198\nsamples = 18\nvalue = [2, 16]'),
 Text(0.7066189624329159, 0.5833333333333334, 'x[32] <= 0.433\ngini = 0.111\nsamples = 17\nvalue = [1, 16]'),
 Text(0.6994633273703041, 0.5277777777777778, 'gini = 0.0\nsamples = 15\nvalue = [0, 15]'),
 Text(0.7137745974955277, 0.5277777777777778, 'x[31] <= 0.25\ngini = 0.5\nsamples = 2\nvalue = [1, 1]'),
 Text(0.7066189624329159, 0.4722222222222222, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.7209302325581395, 0.4722222222222222, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.7209302325581395, 0.5833333333333334, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.7549194991055456, 0.75, 'x[0] <= 0.202\ngini = 0.466\nsamples = 54\nvalue = [34, 20]'),
 Text(0.7352415026833632, 0.6944444444444444, 'x[8] <= 0.164\ngini = 0.245\nsamples = 7\nvalue = [1, 6]'),
 Text(0.7280858676207513, 0.6388888888888888, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.7423971377459749, 0.6388888888888888, 'gini = 0.0\nsamples = 6\nvalue = [0, 6]'),
 Text(0.774597495527728, 0.6944444444444444, 'x[2] <= 0.622\ngini = 0.418\nsamples = 47\nvalue = [33, 14]'),
 Text(0.7567084078711985, 0.6388888888888888, 'x[2] <= 0.145\ngini = 0.482\nsamples = 32\nvalue = [19, 13]'),
 Text(0.7423971377459749, 0.5833333333333334, 'x[2] <= 0.024\ngini = 0.18\nsamples = 10\nvalue = [9, 1]'),
 Text(0.7352415026833632, 0.5277777777777778, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.7495527728085868, 0.5277777777777778, 'gini = 0.0\nsamples = 9\nvalue = [9, 0]'),
 Text(0.7710196779964222, 0.5833333333333334, 'x[18] <= 0.87\ngini = 0.496\nsamples = 22\nvalue = [10, 12]'),
 Text(0.7638640429338104, 0.5277777777777778, 'x[8] <= 0.41\ngini = 0.465\nsamples = 19\nvalue = [7, 12]'),
 Text(0.7495527728085868, 0.4722222222222222, 'x[18] <= 0.715\ngini = 0.469\nsamples = 8\nvalue = [5, 3]'),
 Text(0.7423971377459749, 0.4166666666666667, 'gini = 0.0\nsamples = 5\nvalue = [5, 0]'),
 Text(0.7567084078711985, 0.4166666666666667, 'gini = 0.0\nsamples = 3\nvalue = [0, 3]'),
 Text(0.778175313059034, 0.4722222222222222, 'x[0] <= 0.25\ngini = 0.298\nsamples = 11\nvalue = [2, 9]'),
 Text(0.7710196779964222, 0.4166666666666667, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.7853309481216458, 0.4166666666666667, 'x[3] <= 0.25\ngini = 0.18\nsamples = 10\nvalue = [1, 9]'),
 Text(0.778175313059034, 0.3611111111111111, 'x[11] <= 0.286\ngini = 0.5\nsamples = 2\nvalue = [1, 1]'),
 Text(0.7710196779964222, 0.3055555555555556, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.7853309481216458, 0.3055555555555556, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.7924865831842576, 0.3611111111111111, 'gini = 0.0\nsamples = 8\nvalue = [0, 8]'),
 Text(0.778175313059034, 0.5277777777777778, 'gini = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(0.7924865831842576, 0.6388888888888888, 'x[19] <= 0.944\ngini = 0.124\nsamples = 15\nvalue = [14, 1]'),
 Text(0.7853309481216458, 0.5833333333333334, 'gini = 0.0\nsamples = 14\nvalue = [14, 0]'),
 Text(0.7996422182468694, 0.5833333333333334, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.9042933810375671, 0.8055555555555556, 'x[16] <= 0.75\ngini = 0.258\nsamples = 204\nvalue = [173, 31]'),
 Text(0.8479427549194991, 0.75, 'x[17] <= 0.992\ngini = 0.138\nsamples = 147\nvalue = [136, 11]'),
 Text(0.8407871198568873, 0.6944444444444444, 'x[4] <= 0.482\ngini = 0.128\nsamples = 146\nvalue = [136, 10]'),
 Text(0.8211091234347049, 0.6388888888888888, 'x[30] <= 0.063\ngini = 0.038\nsamples = 104\nvalue = [102, 2]'),
 Text(0.813953488372093, 0.5833333333333334, 'x[11] <= 0.193\ngini = 0.32\nsamples = 10\nvalue = [8, 2]'),
 Text(0.8067978533094812, 0.5277777777777778, 'x[28] <= 0.417\ngini = 0.444\nsamples = 3\nvalue = [1, 2]'),
 Text(0.7996422182468694, 0.4722222222222222, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.813953488372093, 0.4722222222222222, 'gini = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(0.8211091234347049, 0.5277777777777778, 'gini = 0.0\nsamples = 7\nvalue = [7, 0]'),
 Text(0.8282647584973166, 0.5833333333333334, 'gini = 0.0\nsamples = 94\nvalue = [94, 0]'),
 Text(0.8604651162790697, 0.6388888888888888, 'x[9] <= 0.167\ngini = 0.308\nsamples = 42\nvalue = [34, 8]'),
 Text(0.8425760286225402, 0.5833333333333334, 'x[18] <= 0.194\ngini = 0.375\nsamples = 4\nvalue = [1, 3]'),
 Text(0.8354203935599285, 0.5277777777777778, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.8497316636851521, 0.5277777777777778, 'gini = 0.0\nsamples = 3\nvalue = [0, 3]'),
 Text(0.8783542039355993, 0.5833333333333334, 'x[0] <= 0.393\ngini = 0.229\nsamples = 38\nvalue = [33, 5]'),
 Text(0.8640429338103757, 0.5277777777777778, 'x[13] <= 0.375\ngini = 0.5\nsamples = 6\nvalue = [3, 3]'),
 Text(0.8568872987477638, 0.4722222222222222, 'x[22] <= 0.036\ngini = 0.375\nsamples = 4\nvalue = [3, 1]'),
 Text(0.8497316636851521, 0.4166666666666667, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.8640429338103757, 0.4166666666666667, 'gini = 0.0\nsamples = 3\nvalue = [3, 0]'),
 Text(0.8711985688729875, 0.4722222222222222, 'gini = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(0.8926654740608229, 0.5277777777777778, 'x[8] <= 0.992\ngini = 0.117\nsamples = 32\nvalue = [30, 2]'),
 Text(0.8855098389982111, 0.4722222222222222, 'x[28] <= 0.917\ngini = 0.062\nsamples = 31\nvalue = [30, 1]'),
 Text(0.8783542039355993, 0.4166666666666667, 'gini = 0.0\nsamples = 30\nvalue = [30, 0]'),
 Text(0.8926654740608229, 0.4166666666666667, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.8998211091234347, 0.4722222222222222, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.855098389982111, 0.6944444444444444, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.960644007155635, 0.75, 'x[14] <= 0.812\ngini = 0.456\nsamples = 57\nvalue = [37, 20]'),
 Text(0.9355992844364938, 0.6944444444444444, 'x[32] <= 0.4\ngini = 0.238\nsamples = 29\nvalue = [25, 4]'),
 Text(0.9212880143112702, 0.6388888888888888, 'x[8] <= 0.071\ngini = 0.142\nsamples = 26\nvalue = [24, 2]'),
 Text(0.9141323792486583, 0.5833333333333334, 'x[10] <= 0.5\ngini = 0.444\nsamples = 3\nvalue = [1, 2]'),
 Text(0.9069767441860465, 0.5277777777777778, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.9212880143112702, 0.5277777777777778, 'gini = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(0.9284436493738819, 0.5833333333333334, 'gini = 0.0\nsamples = 23\nvalue = [23, 0]'),
 Text(0.9499105545617174, 0.6388888888888888, 'x[2] <= 0.324\ngini = 0.444\nsamples = 3\nvalue = [1, 2]'),
 Text(0.9427549194991055, 0.5833333333333334, 'gini = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(0.9570661896243292, 0.5833333333333334, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.9856887298747764, 0.6944444444444444, 'x[32] <= 0.1\ngini = 0.49\nsamples = 28\nvalue = [12, 16]'),
 Text(0.9785330948121646, 0.6388888888888888, 'x[12] <= 0.833\ngini = 0.48\nsamples = 20\nvalue = [12, 8]'),
 Text(0.9713774597495528, 0.5833333333333334, 'x[4] <= 0.018\ngini = 0.415\nsamples = 17\nvalue = [12, 5]'),
 Text(0.964221824686941, 0.5277777777777778, 'gini = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(0.9785330948121646, 0.5277777777777778, 'x[17] <= 0.365\ngini = 0.32\nsamples = 15\nvalue = [12, 3]'),
 Text(0.9713774597495528, 0.4722222222222222, 'gini = 0.0\nsamples = 11\nvalue = [11, 0]'),
 Text(0.9856887298747764, 0.4722222222222222, 'x[18] <= 0.702\ngini = 0.375\nsamples = 4\nvalue = [1, 3]'),
 Text(0.9785330948121646, 0.4166666666666667, 'gini = 0.0\nsamples = 3\nvalue = [0, 3]'),
 Text(0.9928443649373881, 0.4166666666666667, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]'),
 Text(0.9856887298747764, 0.5833333333333334, 'gini = 0.0\nsamples = 3\nvalue = [0, 3]'),
 Text(0.9928443649373881, 0.6388888888888888, 'gini = 0.0\nsamples = 8\nvalue = [0, 8]')]
In [80]:
from sklearn.model_selection import GridSearchCV
parameter={
 'criterion':['gini','entropy'],
  'splitter':['best','random'],
  'max_depth':[1,2,3,4,5],
  'max_features':['auto', 'sqrt', 'log2']

}
In [81]:
grid_search=GridSearchCV(estimator=dtc,param_grid=parameter,cv=5,scoring="accuracy")
In [82]:
grid_search.fit(x_train,y_train)

C:\Users\Manu\OneDrive\Documents\Anaconda\Lib\site-packages\sklearn\model_selection\_validation.py:425: FitFailedWarning: 
100 fits failed out of a total of 300.
The score on these train-test partitions for these parameters will be set to nan.
If these failures are not expected, you can try to debug them by setting error_score='raise'.

Below are more details about the failures:
--------------------------------------------------------------------------------
100 fits failed with the following error:
Traceback (most recent call last):
  File "C:\Users\Manu\OneDrive\Documents\Anaconda\Lib\site-packages\sklearn\model_selection\_validation.py", line 732, in _fit_and_score
    estimator.fit(X_train, y_train, **fit_params)
  File "C:\Users\Manu\OneDrive\Documents\Anaconda\Lib\site-packages\sklearn\base.py", line 1144, in wrapper
    estimator._validate_params()
  File "C:\Users\Manu\OneDrive\Documents\Anaconda\Lib\site-packages\sklearn\base.py", line 637, in _validate_params
    validate_parameter_constraints(
  File "C:\Users\Manu\OneDrive\Documents\Anaconda\Lib\site-packages\sklearn\utils\_param_validation.py", line 95, in validate_parameter_constraints
    raise InvalidParameterError(
sklearn.utils._param_validation.InvalidParameterError: The 'max_features' parameter of DecisionTreeClassifier must be an int in the range [1, inf), a float in the range (0.0, 1.0], a str among {'sqrt', 'log2'} or None. Got 'auto' instead.

  warnings.warn(some_fits_failed_message, FitFailedWarning)
C:\Users\Manu\OneDrive\Documents\Anaconda\Lib\site-packages\sklearn\model_selection\_search.py:976: UserWarning: One or more of the test scores are non-finite: [       nan        nan 0.84013704 0.84013704 0.84013704 0.84013704
        nan        nan 0.84268662 0.84352687 0.84098449 0.84013704
        nan        nan 0.83928597 0.8409881  0.83587811 0.83843491
        nan        nan 0.84182113 0.82994591 0.83247025 0.83671836
        nan        nan 0.82056978 0.83333213 0.83755499 0.83163361
        nan        nan 0.84013704 0.84013704 0.84013704 0.84013704
        nan        nan 0.84013704 0.84013704 0.84013704 0.83928958
        nan        nan 0.83928958 0.84354129 0.83335016 0.84269383
        nan        nan 0.83928958 0.83759827 0.82994951 0.83929318
        nan        nan 0.83758024 0.82312297 0.84099892 0.83163361]
  warnings.warn(
Out[82]:
GridSearchCV(cv=5, estimator=DecisionTreeClassifier(),
             param_grid={'criterion': ['gini', 'entropy'],
                         'max_depth': [1, 2, 3, 4, 5],
                         'max_features': ['auto', 'sqrt', 'log2'],
                         'splitter': ['best', 'random']},
             scoring='accuracy')
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
GridSearchCV(cv=5, estimator=DecisionTreeClassifier(),
             param_grid={'criterion': ['gini', 'entropy'],
                         'max_depth': [1, 2, 3, 4, 5],
                         'max_features': ['auto', 'sqrt', 'log2'],
                         'splitter': ['best', 'random']},
             scoring='accuracy')
DecisionTreeClassifier()
DecisionTreeClassifier()
In [83]:
grid_search.best_params_
Out[83]:
{'criterion': 'entropy',
 'max_depth': 3,
 'max_features': 'sqrt',
 'splitter': 'random'}
In [84]:
dtc_cv=DecisionTreeClassifier(criterion= 'entropy',
 max_depth=3,
 max_features='sqrt',
 splitter='best')
dtc_cv.fit(x_train,y_train)
Out[84]:
DecisionTreeClassifier(criterion='entropy', max_depth=3, max_features='sqrt')
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
DecisionTreeClassifier(criterion='entropy', max_depth=3, max_features='sqrt')
In [85]:
pred=dtc_cv.predict(x_test)
In [86]:
print(classification_report(y_test,pred))

              precision    recall  f1-score   support

           0       0.85      0.99      0.91       245
           1       0.71      0.10      0.18        49

    accuracy                           0.84       294
   macro avg       0.78      0.55      0.55       294
weighted avg       0.82      0.84      0.79       294

Random Forest¶

In [87]:
from sklearn.ensemble import RandomForestClassifier
rfc=RandomForestClassifier()
In [88]:
forest_params = [{'max_depth': list(range(10, 15)), 'max_features': list(range(0,14))}]
In [89]:
rfc_cv= GridSearchCV(rfc,param_grid=forest_params,cv=10,scoring="accuracy")
In [90]:
rfc_cv.fit(x_train,y_train) 

C:\Users\Manu\OneDrive\Documents\Anaconda\Lib\site-packages\sklearn\model_selection\_validation.py:425: FitFailedWarning: 
50 fits failed out of a total of 700.
The score on these train-test partitions for these parameters will be set to nan.
If these failures are not expected, you can try to debug them by setting error_score='raise'.

Below are more details about the failures:
--------------------------------------------------------------------------------
50 fits failed with the following error:
Traceback (most recent call last):
  File "C:\Users\Manu\OneDrive\Documents\Anaconda\Lib\site-packages\sklearn\model_selection\_validation.py", line 732, in _fit_and_score
    estimator.fit(X_train, y_train, **fit_params)
  File "C:\Users\Manu\OneDrive\Documents\Anaconda\Lib\site-packages\sklearn\base.py", line 1144, in wrapper
    estimator._validate_params()
  File "C:\Users\Manu\OneDrive\Documents\Anaconda\Lib\site-packages\sklearn\base.py", line 637, in _validate_params
    validate_parameter_constraints(
  File "C:\Users\Manu\OneDrive\Documents\Anaconda\Lib\site-packages\sklearn\utils\_param_validation.py", line 95, in validate_parameter_constraints
    raise InvalidParameterError(
sklearn.utils._param_validation.InvalidParameterError: The 'max_features' parameter of RandomForestClassifier must be an int in the range [1, inf), a float in the range (0.0, 1.0], a str among {'sqrt', 'log2'} or None. Got 0 instead.

  warnings.warn(some_fits_failed_message, FitFailedWarning)
C:\Users\Manu\OneDrive\Documents\Anaconda\Lib\site-packages\sklearn\model_selection\_search.py:976: UserWarning: One or more of the test scores are non-finite: [       nan 0.84949297 0.85798204 0.85459221 0.85798204 0.85969144
 0.86052441 0.86308127 0.85541793 0.85457772 0.85712734 0.85627988
 0.8605389  0.85627264        nan 0.84694336 0.85205708 0.85883674
 0.85969144 0.85882225 0.85798928 0.85882949 0.85798204 0.86052441
 0.86479067 0.85966971 0.85458496 0.85966247        nan 0.84864552
 0.85544691 0.85800377 0.85882949 0.85796755 0.85967695 0.86138635
 0.86052441 0.8596842  0.86054614 0.85798928 0.85882225 0.85796755
        nan 0.84779082 0.85714907 0.85885122 0.86051717 0.86052441
 0.85881501 0.85882225 0.86223381 0.85712734 0.85883674 0.86137911
 0.85540345 0.85627264        nan 0.84864552 0.85375199 0.85544691
 0.85628712 0.8596842  0.85627988 0.8622483  0.86137187 0.85796031
 0.85881501 0.85627264 0.86051717 0.85541793]
  warnings.warn(
Out[90]:
GridSearchCV(cv=10, estimator=RandomForestClassifier(),
             param_grid=[{'max_depth': [10, 11, 12, 13, 14],
                          'max_features': [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11,
                                           12, 13]}],
             scoring='accuracy')
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
GridSearchCV(cv=10, estimator=RandomForestClassifier(),
             param_grid=[{'max_depth': [10, 11, 12, 13, 14],
                          'max_features': [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11,
                                           12, 13]}],
             scoring='accuracy')
RandomForestClassifier()
RandomForestClassifier()
In [91]:
pred=rfc_cv.predict(x_test)
In [92]:
print(classification_report(y_test,pred))

              precision    recall  f1-score   support

           0       0.85      0.98      0.91       245
           1       0.67      0.16      0.26        49

    accuracy                           0.85       294
   macro avg       0.76      0.57      0.59       294
weighted avg       0.82      0.85      0.81       294
In [93]:
rfc_cv.best_params_
Out[93]:
{'max_depth': 11, 'max_features': 10}
In [94]:
confusion_matrix(y_test,pred)
Out[94]:
array([[241,   4],
       [ 41,   8]], dtype=int64)
In [95]:
pd.crosstab(y_test,pred)
Out[95]:
col_0 0 1
Attrition
0 241 4
1 41 8
In [96]:
a3 = (240+11)/294 #accuracy
a3
Out[96]:
0.8537414965986394
In [97]:
r3 = 11/(11+38) # recall
r3
Out[97]:
0.22448979591836735
In [98]:
p3 = 11/(5+11) #precision
p3
Out[98]:
0.6875
In [99]:
f3 = 2*r3*p3/(r3+p3) #E1 score
f3
Out[99]:
0.3384615384615384
In [100]:
print(classification_report(y_test,pred))

              precision    recall  f1-score   support

           0       0.85      0.98      0.91       245
           1       0.67      0.16      0.26        49

    accuracy                           0.85       294
   macro avg       0.76      0.57      0.59       294
weighted avg       0.82      0.85      0.81       294